© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192483
    Prev
    Next
    INDEX
    Explanations

    Wilson Family

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized existing measurement attempts prevents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Germany
    0.42
     Tokyo
    0.42
    :
    0.41
     genü
    0.41
     Norden
    0.39
    4
    0.39
     Enough
    0.39
    ?
    0.38
     Cologne
    0.38
     genug
    0.38
    POSITIVE LOGITS
    ोट
    0.48
    itabbo
    0.45
     하지만
    0.45
     उक्त
    0.45
    𝙿
    0.45
    でしたが
    0.43
    ນະ
    0.43
     karit
    0.42
     datafile
    0.42
    یو
    0.41
    Activations Density 0.001%

    No Known Activations